By nhangen
Dispatch long-running research tasks to the Manus AI agent platform from Claude Code via slash command. On-demand polling plus SessionStart hook that surfaces newly-completed tasks on the next session, optional Obsidian filing, explicit-invocation cost gating.
Cancel a running Manus task by id. Usage: /manus-dispatch:cancel <task_id>
Dispatch a long-running research task to the Manus AI agent platform. Returns immediately with a task id; poll later with /manus-dispatch:manus-status. Usage: /manus-dispatch <research query>
Pull current status (and result if completed) for one or all running Manus tasks. Usage: /manus-dispatch:manus-status [task_id]
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub nhangen/claude-plugins --plugin manus-dispatchAutonomous CEO agent for Claude Code. Reads your Obsidian vault, prioritizes work, dispatches 6 specialized subagents, and learns from corrections via playbooks and training files.
Source-grounded project glossary: auto-invokes on unfamiliar terms in registered repos, plus build (seed) and maintain (drift-check) operations.
Auto-summarize and compact when context fill crosses thresholds. Keeps live conversation under 40% by leaning on claude-mem + Obsidian as the durable layer.
Causal tracing layer over claude-mem. Extracts informed_by edges from observation narratives to trace what led to what. 6 MCP tools, 10 edge types.
Scans markdown documentation files against actual behavioral data to find what's missing. Recommends additions to CLAUDE.md, rules, memory, and skills.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex and gemini CLIs when installed) to get diverse perspectives on coding problems
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use